Image processing device, method, and computer program product

• US 9,384,563 B2
• Filed: 06/28/2012
• Issued: 07/05/2016
• Est. Priority Date: 08/04/2011
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Digital Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Takahashi, Shihomi, Nishiyama, Masashi, Shibata, Tomoyuki, Hirohata, Makoto, Sekine, Masahiro, Sugita, Kaoru
• Primary Examiner(s): Rao, Andy
• Application Number:
  US13/535,952
• Publication Number:
  US 20130033591A1
• Time in Patent Office: 1,468 Days
• Field of Search: 348/46, 348/51, 348/61, 348/77, 348/150, 382/207, 382/209, 382217-220
• US Class Current: 1/1
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56

Abstract

In an embodiment, an image processing device includes: a first calculating unit; a selecting unit; an extracting unit; a second calculating unit; a determining unit; and a generating unit. The first calculating unit calculates posture information of a subject from a first image including the subject. The selecting unit selects a second image associated with the posture information from a plurality of second images including clothing. The extracting unit extracts a first feature of the subject from a first contour in the first image and extracts a second feature from a second contour in the second image. The second calculating unit calculates a first difference between the first feature and the second feature. The determining unit determines a transparency that is higher as the first difference is larger. The generating unit generates a composite image combining the first image and the second image with the determined transparency.

Claims

1. An image processing device comprising a plurality of units implemented using a hardware processor, the units including:

a first calculating unit configured to calculate posture information of a subject from a first image including the subject;

a selecting unit configured to select a second image associated with the posture information from a plurality of second images including clothing;

an extracting unit configured to extract a first feature of the subject from a first contour in the first image and extract a second feature from a second contour in the second image;

a second calculating unit configured to calculate a first difference based on respective positions of the first feature and the second feature;

a determining unit configured to determine a transparency that is higher as the first difference is larger; and

a generating unit configured to generate a composite image combining the first image and the second image with the transparency changed to the determined transparency.

2. The device according to claim 1, wherein the units further include a detecting unit configured to detect a motion of the subject, and wherein

the second calculating unit further calculates a second difference between the first features of first images that are successive in time series when the motion is detected, and

the determining unit determines a transparency that is higher as the second difference is larger.

3. The device according to claim 1, wherein the extracting unit extracts at least one of a shoulder and a lower back of the subject as the first feature and the second feature.

4. The device according to claim 1, wherein

the second calculating unit calculates the first difference for each of a plurality of linear regions into which each of the first feature and the second feature is divided, and

the determining unit determines a transparency that is higher as the first difference in each of the linear regions is larger for each region including the linear region in the second image.

5. The device according to claim 1, further comprising storage configured to store the second image.

6. The device according to claim 5, wherein

the storage stores in advance the second image and the second feature in association with each other, and

the extracting unit extracts the second feature by reading the second feature associated with the second image.

7. The device according to claim 6, wherein the units further include a creating unit configured to create at least one of the second image and the second feature.

8. The device according to claim 1;

further comprising a camera configured to capture a subject to acquire the first image.

9. The device according to claim 8, wherein the camera captures the clothing to acquire the second image.

10. The device according to claim 1, wherein the second image is an image acquired by capturing clothing in a state worn by the subject.

11. The device according to claim 1, wherein the units further include an adjusting unit configured to adjust an aspect ratio of at least one of the second image and the first image to an aspect ratio of a mirror to reflect the subject.

12. The device according to claim 1, further comprising an output device configured to output the composite image.

13. The device according to claim 1, wherein the extracting unit

extracts the first contour in the first image and the second contour in the second image by edge extraction,

extracts the first feature and the second feature according to curvatures of the first contour and the second contour, respectively, and

enlarges at least one of the size of a filter used for the edge extraction and the size of an adjacent region used for the calculation of the curvature as the proportion of the first image in a captured image is larger.

16. The device according to claim 1, wherein the extracting unit

extracts the first feature and the second feature according to curvatures of the first contour in the first image and the second contour in the second contour in the second image and according to depth information representing a depth of the subject.

14. An image processing method comprising:

calculating posture information of a subject from a first image including the subject;

selecting a second image associated with the posture information from a plurality of second images including clothing;

extracting a first feature of the subject from a first contour in the first image;

extracting a second feature from a second contour in the second image;

calculating a first difference based on respective positions of the first feature and the second feature;

determining a transparency that is higher as the first difference is larger; and

generating a composite image combining the first image and the second image with the transparency changed to the determined transparency.

15. A computer program product comprising a non-transitory computer-readable medium including programmed instructions embodied therein for image processing, wherein the instructions, when executed by a computer, cause the computer to perform at least:

calculating posture information of a subject from a first image including the subject;

selecting a second image associated with the posture information from a plurality of second images including clothing;

extracting a first feature of the subject from a first contour in the first image;

extracting a second feature from a second contour in the second image;

calculating a first difference based in respective positions of the first feature and the second feature;

determining a transparency that is higher as the first difference is larger; and

generating a composite image combining the first image and the second image with the transparency changed to the determined transparency.

17. An image processing device comprising a plurality of units implemented using a hardware processor, the units including:

a first calculating unit configured to calculate posture information defined by a set of joint angles of a subject from a first image including the subject;

a selecting unit configured to select a second image associated with the posture information from a plurality of second images including clothing;

an extracting unit configured to extract a first feature of the subject from a first contour in the first image and extract a second feature from a second contour in the second image;

a second calculating unit configured to calculate a first difference based on respective positions of the first feature and the second feature;

a determining unit configured to determine a transparency that is higher as the first difference is larger; and

a generating unit configured to generate a composite image combining the first image and the second image with the transparency changed to the determined transparency.

18. An image processing device comprising a plurality of units implemented using a hardware processor, the units including:

a selecting unit configured to select a second image corresponding to a subject included in a first image;

an extracting unit configured to extract a first feature of the first image and extract a second feature of the second image; and

a generating unit configured to, when there is a difference between the first feature and the second feature, determine a transparency of the second image and combine the second image and the first image.

19. An image processing device comprising a plurality of units implemented using a hardware processor, the units including:

a selecting unit configured to select a second image corresponding to a subject included in a first image; and

a generating unit configured to, according to a motion of the subject, determine a transparency of the second image and combine the first image and the second image.